Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 665 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0496. Min Range: -7.0496
Max Act: 7.0496. Min Act: -0.1700
Data Index: 35527 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.9246. Min Act: -0.1700
Data Index: 7555672 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.8621. Min Act: -0.1700
Data Index: 7864059 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.8621. Min Act: -0.1700
Data Index: 3278720 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.7996. Min Act: -0.1700
Data Index: 2984126 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.7683. Min Act: -0.1700
Data Index: 7313871 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.6746. Min Act: -0.1700
Data Index: 4100639 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.6746. Min Act: -0.1700
Data Index: 8785950 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.6433. Min Act: -0.1700
Data Index: 2853374 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.6433. Min Act: -0.1700
Data Index: 7493926 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.6433. Min Act: -0.1700
Data Index: 1257070 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.5808. Min Act: -0.1700
Data Index: 3893213 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.5808. Min Act: -0.1700
Data Index: 6474139 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.5808. Min Act: -0.1700
Data Index: 6909448 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.5496. Min Act: -0.1700
Data Index: 8628453 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.5496. Min Act: -0.1700
Data Index: 1165892 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.5496. Min Act: -0.1700
Data Index: 256676 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.5183. Min Act: -0.1700
Data Index: 3776020 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.4871. Min Act: -0.1700
Data Index: 8049196 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0496. Min Range: -7.0496
Max Act: 6.4871. Min Act: -0.1700
Data Index: 7754363 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19